JACIII Vol.12 No.4 pp. 377-381
doi: 10.20965/jaciii.2008.p0377


Effect of Genetic Encoding on Evolution of Efficient Neural Controllers

Genci Capi

Graduate School of Science and Engineering for Research, University of Toyama, Gofuku Campus, 3190 Gofuku, Toyama 930-8555, Japan

April 23, 2007
June 29, 2007
July 20, 2008
multiobjective optimization, evolution, neural controllers

In this paper, we present a new method based on multiobjective evolutionary algorithms to evolve low complexity neural controllers for the robots that have to perform two different tasks, simultaneously. In our method, each task and the structure of neural controller are considered as separated objective functions. We compare the results of two different encoding schemes: (1) Connectionist encoding and (2) Node based encoding. Simulation results show that multiobjective evolution can be successfully applied to generate low complexity neural controllers. In addition, node based encoding outperformed connectionist encoding in terms of robot performance and robustness of the neural controller.

Cite this article as:
Genci Capi, “Effect of Genetic Encoding on Evolution of Efficient Neural Controllers,” J. Adv. Comput. Intell. Intell. Inform., Vol.12, No.4, pp. 377-381, 2008.
Data files:
  1. [1] R. Schwaiger, H. A. Mayer, and R. Huber, “Evolution of low complexity artificial neural networks for land cover classification from remote sensing data,” Proc. of the 20th workshop of the Austrian Association for Pattern Recognition, pp. 75-86, 1996.
  2. [2] R. Kamimura, “Multi-layered greedy network growing algorithm: extension of greedy network growing algorithm to multi-layered networks,” Int. J. Neural Syst, Vol.14, No.1, pp. 9-26, 2004.
  3. [3] S. Nolfi, “Evolving robots able to self-localize in the environment: The importance of viewing cognition as the result of processes occurring at different time scales,” Connection Science, Vol.14, No.3, pp. 231-244, 2002.
  4. [4] G. Capi, “A New Method for Simultaneous Evolution of Robot Behaviors based on Multiobjective Evolution,” Int. Conf. on Intelligent Robots and Systems, pp. 4133-4137, 2006.
  5. [5] R. Odagiri, Y. Wei, T. Asai, O. Yamakawa, and K. Murase, “Measuring the complexity of the real environment with evolutionary robot: Evolution of a real mobile robot Khepera to have minimal structure,” Proc. IEEE Int. Conf. on Evolutionary Computation (ICEC98), pp. 348-353, 1998.
  6. [6] L. Marti, “Genetically Generated Neural Networks II: Searching for an Optimal Representation,” in: IEEE Int. Joint Conf. on Neural Networks, Vol.2, pp. 221-226, 1992.
  7. [7] V. Maniezzo, “Searching among search spaces: hastening the genetic evolution of feedforward networks,” In Proc. of the Conf. on Artificial Neural Nets and Genetic Algorithms, pp. 635-642, 1993.
  8. [8] J. R. Koza and J. P. Rice, “Genetic Generation of Both the Weights and Architecture for a Neural Network,” In Int. Joint Conf. on Neural Networks, IJCNN-91, Vol.2, pp. 397-404, 1991.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Feb. 25, 2021